Doctor Recommendation in Online Health Forums via Expertise Learning

Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics Volume 1: Long Papers, pages 1111 - 1123 May 22-27, 2022 c⃝2022 Association for Computational Linguistics Doctor Recommendation in Online Health Forums via Expertise Learning Xiaoxin Lu1∗ Yubo Zhang1∗ Jing Li1† Shi Zong2 1Department of Computing, The Hong Kong Polytechnic University, HKSAR, China 2Department of Computer Science and Technology, Nanjing University, Nanjing, China 1{xiaoxin.lu, yubo.zhang}@connect.polyu.hk 1jing-amelia.li@polyu.edu.hk 2szong@nju.edu.cn Abstract Huge volumes of patient queries are daily gen- erated on online health forums, rendering man- ual doctor allocation a labor-intensive task. To better help patients, this paper studies a novel task of doctor recommendation to enable au- tomatic pairing of a patient to a doctor with relevant expertise. While most prior work in recommendation focuses on modeling target users from their past behavior, we can only rely on limited words in a query to infer a pa- tient’s needs for privacy reasons. For doctor modeling, we study the joint effects of their profiles and previous dialogues with other pa- tients and explore their interactions via self- learning. The learned doctor embeddings are further employed to estimate their capabili- ties of handling a patient query with a multi- head attention mechanism. For experiments, a large-scale dataset is collected from Chunyu Yisheng, a Chinese online health forum, where our model exhibits state-of-the-art results, out- performing baselines only considering profiles and past dialogues to characterize a doctor.1 1 Introduction The growing popularity of health communities on social media has revolutionized the traditional doc- tor consultancy paradigm in a face-to-face manner. Massive amounts of patients are now turning to on- line health forums to seek professional help; mean- while, popular healthcare platforms are able to re- cruit a large group of licensed doctors to provide online service (Liu et al., 2020b). In the COVID-19 crisis, the social distancing policies further flourish the use of these forums, where numerous patients would query diverse varieties of health problems every day (Gong et al., 2020). ∗Equal contribution. Yubo Zhang was supported by PolyU Undergraduate Research and Innovation Scheme (URIS). †Jing Li is the corresponding author. 1Our dataset and code are publicly available in: https://github.com/polyusmart/ Doctor-Recommendation Figure 1: The sample patient query q on the top, fol- lowed by the profile of a sample doctor D and three dialogues D engaged before. Salient words indicating patient needs and doctor expertise are in red.2 Nevertheless, in much practice (Cao et al., 2017), manual doctor allocations are adopted to handle each query, largely limiting the efficiency to help patients in sheer quantities and resulting in an ex- tremely expensive process. Under this circum- stance, how can we automate and speed up the pairing of patients to doctors who are able to offer the help? In this paper, we present a novel task of doctor recommendation, whose goal is to automatically figure out a patient’s needs from their query on on- line health forums and recommend a doctor with relevant expertise to help. The solution can not be trivially found from …

Content truncated to 500 words